From fa73898a3d311985713402553e014e0b139892bc Mon Sep 17 00:00:00 2001 From: ntrifunovic Date: Mon, 18 Feb 2013 00:05:43 +0000 Subject: [PATCH] Removing version 1_0 directory git-svn-id: http://svn.code.sf.net/p/utfcpp/code@139 a809a056-fc17-0410-9590-b4f493f8b08e --- v1_0/buildrelease.pl | 18 - v1_0/doc/ReleaseNotes | 11 - v1_0/doc/utf8cpp.html | 1200 - v1_0/samples/Makefile | 5 - v1_0/samples/docsample.cpp | 63 - v1_0/source/utf8.h | 569 - v1_0/test_data/negative/utf8_invalid.txt | Bin 20334 -> 0 bytes v1_0/test_data/utf8samples/UTF-8-demo.txt | 212 - .../utf8samples/Unicode_transcriptions.html | 167 - v1_0/test_data/utf8samples/big.txt | 420160 --------------- v1_0/test_data/utf8samples/quickbrown.txt | 126 - v1_0/test_drivers/Makefile | 19 - v1_0/test_drivers/negative/Makefile | 5 - v1_0/test_drivers/negative/negative.cpp | 39 - v1_0/test_drivers/performance/Makefile | 5 - v1_0/test_drivers/performance/iconvtest.cpp | 125 - v1_0/test_drivers/performance/timer.h | 21 - v1_0/test_drivers/performance/win32.cpp | 105 - v1_0/test_drivers/regression_tests/Makefile | 6 - .../r1_0Beta1/basic_functionality.h | 16 - .../regression_tests/r1_0Beta1/invalidutf8.h | 96 - .../r1_0Beta2/basic_functionality.h | 11 - .../r1_0Beta3/basic_functionality.h | 11 - .../regression_tests/reg_tests_driver.cpp | 40 - v1_0/test_drivers/runtests.pl | 50 - v1_0/test_drivers/smoke_test/Makefile | 5 - v1_0/test_drivers/smoke_test/test.cpp | 235 - v1_0/test_drivers/utf8reader/Makefile | 5 - v1_0/test_drivers/utf8reader/utf8reader.cpp | 134 - 29 files changed, 423459 deletions(-) delete mode 100755 v1_0/buildrelease.pl delete mode 100644 v1_0/doc/ReleaseNotes delete mode 100644 v1_0/doc/utf8cpp.html delete mode 100644 v1_0/samples/Makefile delete mode 100644 v1_0/samples/docsample.cpp delete mode 100644 v1_0/source/utf8.h delete mode 100755 v1_0/test_data/negative/utf8_invalid.txt delete mode 100644 v1_0/test_data/utf8samples/UTF-8-demo.txt delete mode 100644 v1_0/test_data/utf8samples/Unicode_transcriptions.html delete mode 100644 v1_0/test_data/utf8samples/big.txt delete mode 100644 v1_0/test_data/utf8samples/quickbrown.txt delete mode 100644 v1_0/test_drivers/Makefile delete mode 100644 v1_0/test_drivers/negative/Makefile delete mode 100644 v1_0/test_drivers/negative/negative.cpp delete mode 100644 v1_0/test_drivers/performance/Makefile delete mode 100644 v1_0/test_drivers/performance/iconvtest.cpp delete mode 100644 v1_0/test_drivers/performance/timer.h delete mode 100644 v1_0/test_drivers/performance/win32.cpp delete mode 100644 v1_0/test_drivers/regression_tests/Makefile delete mode 100644 v1_0/test_drivers/regression_tests/r1_0Beta1/basic_functionality.h delete mode 100644 v1_0/test_drivers/regression_tests/r1_0Beta1/invalidutf8.h delete mode 100644 v1_0/test_drivers/regression_tests/r1_0Beta2/basic_functionality.h delete mode 100644 v1_0/test_drivers/regression_tests/r1_0Beta3/basic_functionality.h delete mode 100644 v1_0/test_drivers/regression_tests/reg_tests_driver.cpp delete mode 100755 v1_0/test_drivers/runtests.pl delete mode 100644 v1_0/test_drivers/smoke_test/Makefile delete mode 100644 v1_0/test_drivers/smoke_test/test.cpp delete mode 100644 v1_0/test_drivers/utf8reader/Makefile delete mode 100644 v1_0/test_drivers/utf8reader/utf8reader.cpp diff --git a/v1_0/buildrelease.pl b/v1_0/buildrelease.pl deleted file mode 100755 index 6df3ed9..0000000 --- a/v1_0/buildrelease.pl +++ /dev/null @@ -1,18 +0,0 @@ -#! /usr/bin/perl - -$release_files = 'source/utf8.h doc/utf8cpp.html doc/ReleaseNotes'; - -# First get the latest version -`svn update`; - -# Then construct the name of the zip file -$argc = @ARGV; -if ($argc > 0) { - $zip_name = $ARGV[0]; -} -else { - $zip_name = "utf8"; -} - -# Zip the files to an archive -`zip $zip_name $release_files`; diff --git a/v1_0/doc/ReleaseNotes b/v1_0/doc/ReleaseNotes deleted file mode 100644 index 07ad692..0000000 --- a/v1_0/doc/ReleaseNotes +++ /dev/null @@ -1,11 +0,0 @@ -utf8 cpp library -Release 1.02 - -utf8::previous is deprecated in favor of utf8::prior - -Bug Fixes: -[ 1599048 ] utf8::previous doesn't play well with Standard containers - - -Files: utf8.h utf8cpp.html ReleaseNotes - diff --git a/v1_0/doc/utf8cpp.html b/v1_0/doc/utf8cpp.html deleted file mode 100644 index 5376e55..0000000 --- a/v1_0/doc/utf8cpp.html +++ /dev/null @@ -1,1200 +0,0 @@ - - - - - - - - - UTF8-CPP: UTF-8 with C++ in a Portable Way - - - - -

- The Sourceforge project page -

-
-

- Table of Contents -

- -
-

- Introduction -

-

- Many C++ developers miss an easy and portable way of handling Unicode encoded - strings. C++ Standard is currently Unicode agnostic, and while some work is being - done to introduce Unicode to the next incarnation called C++0x, for the moment - nothing of the sort is available. In the meantime, developers use 3rd party - libraries like ICU, OS specific capabilities, or simply roll out their own - solutions. -

-

- In order to easily handle UTF-8 encoded Unicode strings, I have come up with a set - of template functions. For anybody used to work with STL algorithms, they should be - easy and natural to use. The code is freely available for any purpose - check out - the license at the beginning of the utf8.h file. If you run into - bugs or performance issues, please let me know and I'll do my best to address them. -

-

- The purpose of this article is not to offer an introduction to Unicode in general, - and UTF-8 in particular. If you are not familiar with Unicode, be sure to check out - Unicode Home Page or some other source of - information for Unicode. Also, it is not my aim to advocate the use of UTF-8 - encoded strings in C++ programs; if you want to handle UTF-8 encoded strings from - C++, I am sure you have good reasons for it. -

-

- Examples of use -

-

- To illustrate the use of this utf8 library, we shall open a file containing UTF-8 - encoded text, check whether it starts with a byte order mark, read each line into a - std::string, check it for validity, convert the text to UTF-16, and - back to UTF-8: -

-
-#include <fstream>
-#include <iostream>
-#include <string>
-#include <vector>
-#include "utf8.h"
-using namespace std;
-int main()
-{
-    if (argc != 2) {
-        cout << "\nUsage: docsample filename\n";
-        return 0;
-    }
-    const char* test_file_path = argv[1];
-    // Open the test file (must be UTF-8 encoded)
-    ifstream fs8(test_file_path);
-    if (!fs8.is_open()) {
-    cout << "Could not open " << test_file_path << endl;
-    return 0;
-    }
-    // Read the first line of the file
-    unsigned line_count = 1;
-    string line;
-    if (!getline(fs8, line)) 
-        return 0;
-    // Look for utf-8 byte-order mark at the beginning
-    if (line.size() > 2) {
-        if (utf8::is_bom(line.c_str()))
-            cout << "There is a byte order mark at the beginning of the file\n";
-    }
-    // Play with all the lines in the file
-    do {
-       // check for invalid utf-8 (for a simple yes/no check, there is also utf8::is_valid function)
-        string::iterator end_it = utf8::find_invalid(line.begin(), line.end());
-        if (end_it != line.end()) {
-            cout << "Invalid UTF-8 encoding detected at line " << line_count << "\n";
-            cout << "This part is fine: " << string(line.begin(), end_it) << "\n";
-        }
-        // Get the line length (at least for the valid part)
-        int length = utf8::distance(line.begin(), end_it);
-        cout << "Length of line " << line_count << " is " << length <<  "\n";
-        // Convert it to utf-16
-        vector<unsigned short> utf16line;
-        utf8::utf8to16(line.begin(), end_it, back_inserter(utf16line));
-        // And back to utf-8
-        string utf8line; 
-        utf8::utf16to8(utf16line.begin(), utf16line.end(), back_inserter(utf8line));
-        // Confirm that the conversion went OK:
-        if (utf8line != string(line.begin(), end_it))
-            cout << "Error in UTF-16 conversion at line: " << line_count << "\n";        
-        getline(fs8, line);
-        line_count++;
-    } while (!fs8.eof());
-    return 0;
-}
-
-

- In the previous code sample, we have seen the use of the following functions from - utf8 namespace: first we used is_bom function to detect - UTF-8 byte order mark at the beginning of the file; then for each line we performed - a detection of invalid UTF-8 sequences with find_invalid; the number - of characters (more precisely - the number of Unicode code points) in each line was - determined with a use of utf8::distance; finally, we have converted - each line to UTF-16 encoding with utf8to16 and back to UTF-8 with - utf16to8. -

-

- Reference -

-

- Functions From utf8 Namespace -

-

- utf8::append -

-

- Encodes a 32 bit code point as a UTF-8 sequence of octets and appends the sequence - to a UTF-8 string. -

-
-template <typename octet_iterator>
-octet_iterator append(uint32_t cp, octet_iterator result);
-   
-
-

- cp: A 32 bit integer representing a code point to append to the - sequence.
- result: An output iterator to the place in the sequence where to - append the code point.
- Return value: An iterator pointing to the place - after the newly appended sequence. -

-

- Example of use: -

-
-unsigned char u[5] = {0,0,0,0,0};
-unsigned char* end = append(0x0448, u);
-assert (u[0] == 0xd1 && u[1] == 0x88 && u[2] == 0 && u[3] == 0 && u[4] == 0);
-
-

- Note that append does not allocate any memory - it is the burden of - the caller to make sure there is enough memory allocated for the operation. To make - things more interesting, append can add anywhere between 1 and 4 - octets to the sequence. In practice, you would most often want to use - std::back_inserter to ensure that the necessary memory is allocated. -

-

- In case of an invalid code point, a utf8::invalid_code_point exception - is thrown. -

-

- utf8::next -

-

- Given the iterator to the beginning of the UTF-8 sequence, it returns the code - point and moves the iterator to the next position. -

-
-template <typename octet_iterator> 
-uint32_t next(octet_iterator& it, octet_iterator end);
-   
-
-

- it: a reference to an iterator pointing to the beginning of an UTF-8 - encoded code point. After the function returns, it is incremented to point to the - beginning of the next code point.
- end: end of the UTF-8 sequence to be processed. If it - gets equal to end during the extraction of a code point, an - utf8::not_enough_room exception is thrown.
- Return value: the 32 bit representation of the - processed UTF-8 code point. -

-

- Example of use: -

-
-char* twochars = "\xe6\x97\xa5\xd1\x88";
-char* w = twochars;
-int cp = next(w, twochars + 6);
-assert (cp == 0x65e5);
-assert (w == twochars + 3);
-
-

- This function is typically used to iterate through a UTF-8 encoded string. -

-

- In case of an invalid UTF-8 seqence, a utf8::invalid_utf8 exception is - thrown. -

-

- utf8::prior -

-

- Given a reference to an iterator pointing to an octet in a UTF-8 seqence, it - decreases the iterator until it hits the beginning of the previous UTF-8 encoded - code point and returns the 32 bits representation of the code point. -

-
-template <typename octet_iterator> 
-uint32_t prior(octet_iterator& it, octet_iterator start);
-   
-
-

- it: a reference pointing to an octet within a UTF-8 encoded string. - After the function returns, it is decremented to point to the beginning of the - previous code point.
- start: an iterator to the beginning of the sequence where the search - for the beginning of a code point is performed. It is a - safety measure to prevent passing the beginning of the string in the search for a - UTF-8 lead octet.
- Return value: the 32 bit representation of the - previous code point. -

-

- Example of use: -

-
-char* twochars = "\xe6\x97\xa5\xd1\x88";
-unsigned char* w = twochars + 3;
-int cp = prior (w, twochars);
-assert (cp == 0x65e5);
-assert (w == twochars);
-
-

- This function has two purposes: one is two iterate backwards through a UTF-8 - encoded string. Note that it is usually a better idea to iterate forward instead, - since utf8::next is faster. The second purpose is to find a beginning - of a UTF-8 sequence if we have a random position within a string. -

-

- it will typically point to the beginning of - a code point, and start will point to the - beginning of the string to ensure we don't go backwards too far. it is - decreased until it points to a lead UTF-8 octet, and then the UTF-8 sequence - beginning with that octet is decoded to a 32 bit representation and returned. -

-

- In case pass_end is reached before a UTF-8 lead octet is hit, or if an - invalid UTF-8 sequence is started by the lead octet, an invalid_utf8 - exception is thrown. -

-

- utf8::previous (deprecated, see utf8::prior) -

-

- Given a reference to an iterator pointing to an octet in a UTF-8 seqence, it - decreases the iterator until it hits the beginning of the previous UTF-8 encoded - code point and returns the 32 bits representation of the code point. -

-
-template <typename octet_iterator> 
-uint32_t previous(octet_iterator& it, octet_iterator pass_start);
-   
-
-

- it: a reference pointing to an octet within a UTF-8 encoded string. - After the function returns, it is decremented to point to the beginning of the - previous code point.
- pass_start: an iterator to the point in the sequence where the search - for the beginning of a code point is aborted if no result was reached. It is a - safety measure to prevent passing the beginning of the string in the search for a - UTF-8 lead octet.
- Return value: the 32 bit representation of the - previous code point. -

-

- Example of use: -

-
-char* twochars = "\xe6\x97\xa5\xd1\x88";
-unsigned char* w = twochars + 3;
-int cp = previous (w, twochars - 1);
-assert (cp == 0x65e5);
-assert (w == twochars);
-
-

- utf8::previous is deprecated, and utf8::prior should - be used instead, although the existing code can continue using this function. - The problem is the parameter pass_start that points to the position - just before the beginning of the sequence. Standard containers don't have the - concept of "pass start" and the function can not be used with their iterators. -

-

- it will typically point to the beginning of - a code point, and pass_start will point to the octet just before the - beginning of the string to ensure we don't go backwards too far. it is - decreased until it points to a lead UTF-8 octet, and then the UTF-8 sequence - beginning with that octet is decoded to a 32 bit representation and returned. -

-

- In case pass_end is reached before a UTF-8 lead octet is hit, or if an - invalid UTF-8 sequence is started by the lead octet, an invalid_utf8 - exception is thrown -

-

- utf8::advance -

-

- Advances an iterator by the specified number of code points within an UTF-8 - sequence. -

-
-template <typename octet_iterator, typename distance_type> 
-void advance (octet_iterator& it, distance_type n, octet_iterator end);
-   
-
-

- it: a reference to an iterator pointing to the beginning of an UTF-8 - encoded code point. After the function returns, it is incremented to point to the - nth following code point.
- n: a positive integer that shows how many code points we want to - advance.
- end: end of the UTF-8 sequence to be processed. If it - gets equal to end during the extraction of a code point, an - utf8::not_enough_room exception is thrown.
-

-

- Example of use: -

-
-char* twochars = "\xe6\x97\xa5\xd1\x88";
-unsigned char* w = twochars;
-advance (w, 2, twochars + 6);
-assert (w == twochars + 5);
-
-

- This function works only "forward". In case of a negative n, there is - no effect. -

-

- In case of an invalid code point, a utf8::invalid_code_point exception - is thrown. -

-

- utf8::distance -

-

- Given the iterators to two UTF-8 encoded code points in a seqence, returns the - number of code points between them. -

-
-template <typename octet_iterator> 
-typename std::iterator_traits<octet_iterator>::difference_type distance (octet_iterator first, octet_iterator last);
-   
-
-

- first: an iterator to a beginning of a UTF-8 encoded code point.
- last: an iterator to a "post-end" of the last UTF-8 encoded code - point in the sequence we are trying to determine the length. It can be the - beginning of a new code point, or not.
- Return value the distance between the iterators, - in code points. -

-

- Example of use: -

-
-char* twochars = "\xe6\x97\xa5\xd1\x88";
-size_t dist = utf8::distance(twochars, twochars + 5);
-assert (dist == 2);
-
-

- This function is used to find the length (in code points) of a UTF-8 encoded - string. The reason it is called distance, rather than, say, - length is mainly because developers are used that length is an - O(1) function. Computing the length of an UTF-8 string is a linear operation, and - it looked better to model it after std::distance algorithm. -

-

- In case of an invalid UTF-8 seqence, a utf8::invalid_utf8 exception is - thrown. If last does not point to the past-of-end of a UTF-8 seqence, - a utf8::not_enough_room exception is thrown. -

-

- utf8::utf16to8 -

-

- Converts a UTF-16 encoded string to UTF-8. -

-
-template <typename u16bit_iterator, typename octet_iterator>
-octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result);
-   
-
-

- start: an iterator pointing to the beginning of the UTF-16 encoded - string to convert.
- end: an iterator pointing to pass-the-end of the UTF-16 encoded - string to convert.
- result: an output iterator to the place in the UTF-8 string where to - append the result of conversion.
- Return value: An iterator pointing to the place - after the appended UTF-8 string. -

-

- Example of use: -

-
-unsigned short utf16string[] = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e};
-vector<unsigned char> utf8result;
-utf16to8(utf16string, utf16string + 5, back_inserter(utf8result));
-assert (utf8result.size() == 10);    
-
-

- In case of invalid UTF-16 sequence, a utf8::invalid_utf16 exception is - thrown. -

-

- utf8::utf8to16 -

-

- Converts an UTF-8 encoded string to UTF-16 -

-
-template <typename u16bit_iterator, typename octet_iterator>
-u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result);
-   
-
-

- start: an iterator pointing to the beginning of the UTF-8 encoded - string to convert. < br /> end: an iterator pointing to - pass-the-end of the UTF-8 encoded string to convert.
- result: an output iterator to the place in the UTF-16 string where to - append the result of conversion.
- Return value: An iterator pointing to the place - after the appended UTF-16 string. -

-

- Example of use: -

-
-char utf8_with_surrogates[] = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e";
-vector <unsigned short> utf16result;
-utf8to16(utf8_with_surrogates, utf8_with_surrogates + 9, back_inserter(utf16result));
-assert (utf16result.size() == 4);
-assert (utf16result[2] == 0xd834);
-assert (utf16result[3] == 0xdd1e);
-
-

- In case of an invalid UTF-8 seqence, a utf8::invalid_utf8 exception is - thrown. If end does not point to the past-of-end of a UTF-8 seqence, a - utf8::not_enough_room exception is thrown. -

-

- utf8::utf32to8 -

-

- Converts a UTF-32 encoded string to UTF-8. -

-
-template <typename octet_iterator, typename u32bit_iterator>
-octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result);
-   
-
-

- start: an iterator pointing to the beginning of the UTF-32 encoded - string to convert.
- end: an iterator pointing to pass-the-end of the UTF-32 encoded - string to convert.
- result: an output iterator to the place in the UTF-8 string where to - append the result of conversion.
- Return value: An iterator pointing to the place - after the appended UTF-8 string. -

-

- Example of use: -

-
-int utf32string[] = {0x448, 0x65E5, 0x10346, 0};
-vector<unsigned char> utf8result;
-utf32to8(utf32string, utf32string + 3, back_inserter(utf8result));
-assert (utf8result.size() == 9);
-
-

- In case of invalid UTF-32 string, a utf8::invalid_code_point exception - is thrown. -

-

- utf8::utf8to32 -

-

- Converts a UTF-8 encoded string to UTF-32. -

-
-template <typename octet_iterator, typename u32bit_iterator>
-u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result);
-   
-
-

- start: an iterator pointing to the beginning of the UTF-8 encoded - string to convert.
- end: an iterator pointing to pass-the-end of the UTF-8 encoded string - to convert.
- result: an output iterator to the place in the UTF-32 string where to - append the result of conversion.
- Return value: An iterator pointing to the place - after the appended UTF-32 string. -

-

- Example of use: -

-
-char* twochars = "\xe6\x97\xa5\xd1\x88";
-vector<int> utf32result;
-utf8to32(twochars, twochars + 5, back_inserter(utf32result));
-assert (utf32result.size() == 2);
-
-

- In case of an invalid UTF-8 seqence, a utf8::invalid_utf8 exception is - thrown. If end does not point to the past-of-end of a UTF-8 seqence, a - utf8::not_enough_room exception is thrown. -

-

- utf8::find_invalid -

-

- Detects an invalid sequence within a UTF-8 string. -

-
-template <typename octet_iterator> 
-octet_iterator find_invalid(octet_iterator start, octet_iterator end);
-
-

- start: an iterator pointing to the beginning of the UTF-8 string to - test for validity.
- end: an iterator pointing to pass-the-end of the UTF-8 string to test - for validity.
- Return value: an iterator pointing to the first - invalid octet in the UTF-8 string. In case none were found, equals - end. -

-

- Example of use: -

-
-char utf_invalid[] = "\xe6\x97\xa5\xd1\x88\xfa";
-char* invalid = find_invalid(utf_invalid, utf_invalid + 6);
-assert (invalid == utf_invalid + 5);
-
-

- This function is typically used to make sure a UTF-8 string is valid before - processing it with other functions. It is especially important to call it if before - doing any of the unchecked operations on it. -

-

- utf8::is_valid -

-

- Checks whether a sequence of octets is a valid UTF-8 string. -

-
-template <typename octet_iterator> 
-bool is_valid(octet_iterator start, octet_iterator end);
-   
-
-

- start: an iterator pointing to the beginning of the UTF-8 string to - test for validity.
- end: an iterator pointing to pass-the-end of the UTF-8 string to test - for validity.
- Return value: true if the sequence - is a valid UTF-8 string; false if not. -

- Example of use: -
-char utf_invalid[] = "\xe6\x97\xa5\xd1\x88\xfa";
-bool bvalid = is_valid(utf_invalid, utf_invalid + 6);
-assert (bvalid == false);
-
-

- is_valid is a shorthand for find_invalid(start, end) == - end;. You may want to use it to make sure that a byte seqence is a valid - UTF-8 string without the need to know where it fails if it is not valid. -

-

- utf8::is_bom -

-

- Checks whether a sequence of three octets is a UTF-8 byte order mark (BOM) -

-
-template <typename octet_iterator> 
-bool is_bom (octet_iterator it);
-
-

- it: beginning of the 3-octet sequence to check
- Return value: true if the sequence - is UTF-8 byte order mark; false if not. -

-

- Example of use: -

-
-unsigned char byte_order_mark[] = {0xef, 0xbb, 0xbf};
-bool bbom = is_bom(byte_order_mark);
-assert (bbom == true);
-
-

- The typical use of this function is to check the first three bytes of a file. If - they form the UTF-8 BOM, we want to skip them before processing the actual UTF-8 - encoded text. -

-

- Functions From utf8::unchecked Namespace -

-

- utf8::unchecked::append -

-

- Encodes a 32 bit code point as a UTF-8 sequence of octets and appends the sequence - to a UTF-8 string. -

-
-template <typename octet_iterator>
-octet_iterator append(uint32_t cp, octet_iterator result);
-   
-
-

- cp: A 32 bit integer representing a code point to append to the - sequence.
- result: An output iterator to the place in the sequence where to - append the code point.
- Return value: An iterator pointing to the place - after the newly appended sequence. -

-

- Example of use: -

-
-unsigned char u[5] = {0,0,0,0,0};
-unsigned char* end = unchecked::append(0x0448, u);
-assert (u[0] == 0xd1 && u[1] == 0x88 && u[2] == 0 && u[3] == 0 && u[4] == 0);
-
-

- This is a faster but less safe version of utf8::append. It does not - check for validity of the supplied code point, and may produce an invalid UTF-8 - sequence. -

-

- utf8::unchecked::next -

-

- Given the iterator to the beginning of a UTF-8 sequence, it returns the code point - and moves the iterator to the next position. -

-
-template <typename octet_iterator>
-uint32_t next(octet_iterator& it);
-   
-
-

- it: a reference to an iterator pointing to the beginning of an UTF-8 - encoded code point. After the function returns, it is incremented to point to the - beginning of the next code point.
- Return value: the 32 bit representation of the - processed UTF-8 code point. -

-

- Example of use: -

-
-char* twochars = "\xe6\x97\xa5\xd1\x88";
-char* w = twochars;
-int cp = unchecked::next(w);
-assert (cp == 0x65e5);
-assert (w == twochars + 3);
-
-

- This is a faster but less safe version of utf8::next. It does not - check for validity of the supplied UTF-8 sequence. -

-

- utf8::unchecked::prior -

-

- Given a reference to an iterator pointing to an octet in a UTF-8 seqence, it - decreases the iterator until it hits the beginning of the previous UTF-8 encoded - code point and returns the 32 bits representation of the code point. -

-
-template <typename octet_iterator>
-uint32_t prior(octet_iterator& it);
-   
-
-

- it: a reference pointing to an octet within a UTF-8 encoded string. - After the function returns, it is decremented to point to the beginning of the - previous code point.
- Return value: the 32 bit representation of the - previous code point. -

-

- Example of use: -

-
-char* twochars = "\xe6\x97\xa5\xd1\x88";
-char* w = twochars + 3;
-int cp = unchecked::prior (w);
-assert (cp == 0x65e5);
-assert (w == twochars);
-
-

- This is a faster but less safe version of utf8::prior. It does not - check for validity of the supplied UTF-8 sequence and offers no boundary checking. -

-

- utf8::unchecked::previous (deprecated, see utf8::unchecked::prior) -

-

- Given a reference to an iterator pointing to an octet in a UTF-8 seqence, it - decreases the iterator until it hits the beginning of the previous UTF-8 encoded - code point and returns the 32 bits representation of the code point. -

-
-template <typename octet_iterator>
-uint32_t previous(octet_iterator& it);
-   
-
-

- it: a reference pointing to an octet within a UTF-8 encoded string. - After the function returns, it is decremented to point to the beginning of the - previous code point.
- Return value: the 32 bit representation of the - previous code point. -

-

- Example of use: -

-
-char* twochars = "\xe6\x97\xa5\xd1\x88";
-char* w = twochars + 3;
-int cp = unchecked::previous (w);
-assert (cp == 0x65e5);
-assert (w == twochars);
-
-

- The reason this function is deprecated is just the consistency with the "checked" - versions, where prior should be used instead of previous. - In fact, unchecked::previous behaves exactly the same as - unchecked::prior -

-

- This is a faster but less safe version of utf8::previous. It does not - check for validity of the supplied UTF-8 sequence and offers no boundary checking. -

-

- utf8::unchecked::advance -

-

- Advances an iterator by the specified number of code points within an UTF-8 - sequence. -

-
-template <typename octet_iterator, typename distance_type>
-void advance (octet_iterator& it, distance_type n);
-   
-
-

- it: a reference to an iterator pointing to the beginning of an UTF-8 - encoded code point. After the function returns, it is incremented to point to the - nth following code point.
- n: a positive integer that shows how many code points we want to - advance.
-

-

- Example of use: -

-
-char* twochars = "\xe6\x97\xa5\xd1\x88";
-char* w = twochars;
-unchecked::advance (w, 2);
-assert (w == twochars + 5);
-
-

- This function works only "forward". In case of a negative n, there is - no effect. -

-

- This is a faster but less safe version of utf8::advance. It does not - check for validity of the supplied UTF-8 sequence and offers no boundary checking. -

-

- utf8::unchecked::distance -

-

- Given the iterators to two UTF-8 encoded code points in a seqence, returns the - number of code points between them. -

-
-template <typename octet_iterator>
-typename std::iterator_traits<octet_iterator>::difference_type distance (octet_iterator first, octet_iterator last);
-
-

- first: an iterator to a beginning of a UTF-8 encoded code point.
- last: an iterator to a "post-end" of the last UTF-8 encoded code - point in the sequence we are trying to determine the length. It can be the - beginning of a new code point, or not.
- Return value the distance between the iterators, - in code points. -

-

- Example of use: -

-
-char* twochars = "\xe6\x97\xa5\xd1\x88";
-size_t dist = utf8::unchecked::distance(twochars, twochars + 5);
-assert (dist == 2);
-
-

- This is a faster but less safe version of utf8::distance. It does not - check for validity of the supplied UTF-8 sequence. -

-

- utf8::unchecked::utf16to8 -

-

- Converts a UTF-16 encoded string to UTF-8. -

-
-template <typename u16bit_iterator, typename octet_iterator>
-octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result);
-   
-
-

- start: an iterator pointing to the beginning of the UTF-16 encoded - string to convert.
- end: an iterator pointing to pass-the-end of the UTF-16 encoded - string to convert.
- result: an output iterator to the place in the UTF-8 string where to - append the result of conversion.
- Return value: An iterator pointing to the place - after the appended UTF-8 string. -

-

- Example of use: -

-
-unsigned short utf16string[] = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e};
-vector<unsigned char> utf8result;
-unchecked::utf16to8(utf16string, utf16string + 5, back_inserter(utf8result));
-assert (utf8result.size() == 10);    
-
-

- This is a faster but less safe version of utf8::utf16to8. It does not - check for validity of the supplied UTF-16 sequence. -

-

- utf8::unchecked::utf8to16 -

-

- Converts an UTF-8 encoded string to UTF-16 -

-
-template <typename u16bit_iterator, typename octet_iterator>
-u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result);
-   
-
-

- start: an iterator pointing to the beginning of the UTF-8 encoded - string to convert. < br /> end: an iterator pointing to - pass-the-end of the UTF-8 encoded string to convert.
- result: an output iterator to the place in the UTF-16 string where to - append the result of conversion.
- Return value: An iterator pointing to the place - after the appended UTF-16 string. -

-

- Example of use: -

-
-char utf8_with_surrogates[] = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e";
-vector <unsigned short> utf16result;
-unchecked::utf8to16(utf8_with_surrogates, utf8_with_surrogates + 9, back_inserter(utf16result));
-assert (utf16result.size() == 4);
-assert (utf16result[2] == 0xd834);
-assert (utf16result[3] == 0xdd1e);
-
-

- This is a faster but less safe version of utf8::utf8to16. It does not - check for validity of the supplied UTF-8 sequence. -

-

- utf8::unchecked::utf32to8 -

-

- Converts a UTF-32 encoded string to UTF-8. -

-
-template <typename octet_iterator, typename u32bit_iterator>
-octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result);
-   
-
-

- start: an iterator pointing to the beginning of the UTF-32 encoded - string to convert.
- end: an iterator pointing to pass-the-end of the UTF-32 encoded - string to convert.
- result: an output iterator to the place in the UTF-8 string where to - append the result of conversion.
- Return value: An iterator pointing to the place - after the appended UTF-8 string. -

-

- Example of use: -

-
-int utf32string[] = {0x448, 0x65e5, 0x10346, 0};
-vector<unsigned char> utf8result;
-utf32to8(utf32string, utf32string + 3, back_inserter(utf8result));
-assert (utf8result.size() == 9);
-
-

- This is a faster but less safe version of utf8::utf32to8. It does not - check for validity of the supplied UTF-32 sequence. -

-

- utf8::unchecked::utf8to32 -

-

- Converts a UTF-8 encoded string to UTF-32. -

-
-template <typename octet_iterator, typename u32bit_iterator>
-u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result);
-   
-
-

- start: an iterator pointing to the beginning of the UTF-8 encoded - string to convert.
- end: an iterator pointing to pass-the-end of the UTF-8 encoded string - to convert.
- result: an output iterator to the place in the UTF-32 string where to - append the result of conversion.
- Return value: An iterator pointing to the place - after the appended UTF-32 string. -

-

- Example of use: -

-
-char* twochars = "\xe6\x97\xa5\xd1\x88";
-vector<int> utf32result;
-unchecked::utf8to32(twochars, twochars + 5, back_inserter(utf32result));
-assert (utf32result.size() == 2);
-
-

- This is a faster but less safe version of utf8::utf8to32. It does not - check for validity of the supplied UTF-8 sequence. -

-

- Points of interest -

-

- Design goals and decisions -

-

- The library was designed to be: -

-
    -
  1. - Generic: for better or worse, there are many C++ string classes out there, and - the library should work with as many of them as possible. -
    2. -
  2. - Portable: the library should be portable both accross different platforms and - compilers. The only non-portable code is a small section that declares unsigned - integers of different sizes: three typedefs. They can be changed by the users of - the library if they don't match their platform. The default setting should work - for Windows (both 32 and 64 bit), and most 32 bit and 64 bit Unix derivatives. -
    3. -
  3. - Lightweight: follow the "pay only for what you use" guidline. -
    4. -
  4. - Unintrusive: avoid forcing any particular design or even programming style on the - user. This is a library, not a framework. -
    5. -
-

- Alternatives -

-

- In case you want to look into other means of working with UTF-8 strings from C++, - here is the list of solutions I am aware of: -

-
    -
  1. - ICU Library. It is very powerful, - complete, feature-rich, mature, and widely used. Also big, intrusive, - non-generic, and doesn't play well with the Standard Library. I definitelly - recommend looking at ICU even if you don't plan to use it. -
    2. -
  2. - Glib::ustring. - A class specifically made to work with UTF-8 strings, and also feel like - std::string. If you prefer to have yet another string class in your - code, it may be worth a look. Be aware of the licensing issues, though. -
    3. -
  3. - Platform dependent solutions: Windows and POSIX have functions to convert strings - from one encoding to another. That is only a subset of what my library offers, - but if that is all you need it may be good enough, especially given the fact that - these functions are mature and tested in production. -
    4. -
-

- Conclusion -

-

- Until Unicode becomes officially recognized by the C++ Standard Library, we need to - use other means to work with UTF-8 strings. Template functions I describe in this - article may be a good step in this direction. -

-

- References -

-
    -
  1. - The Unicode Consortium. -
    2. -
  2. - ICU Library. -
    3. -
  3. - UTF-8 at Wikipedia -
    4. -
  4. - UTF-8 and Unicode FAQ for - Unix/Linux -
    5. -
- - diff --git a/v1_0/samples/Makefile b/v1_0/samples/Makefile deleted file mode 100644 index 6cdd3c8..0000000 --- a/v1_0/samples/Makefile +++ /dev/null @@ -1,5 +0,0 @@ -CC = g++ -CFLAGS = -g -Wall -pedantic - -docsample: docsample.cpp ../source/utf8.h - $(CC) $(CFLAGS) docsample.cpp -odocsample diff --git a/v1_0/samples/docsample.cpp b/v1_0/samples/docsample.cpp deleted file mode 100644 index fc8f6f3..0000000 --- a/v1_0/samples/docsample.cpp +++ /dev/null @@ -1,63 +0,0 @@ -#include "../source/utf8.h" -#include -#include -#include -#include - - -using namespace std; - -int main(int argc, char** argv) -{ - if (argc != 2) { - cout << "\nUsage: docsample filename\n"; - return 0; - } - const char* test_file_path = argv[1]; - // Open the test file (must be UTF-8 encoded) - ifstream fs8(test_file_path); - if (!fs8.is_open()) { - cout << "Could not open " << test_file_path << endl; - return 0; - } - - // Read the first line of the file - unsigned line_count = 1; - string line; - if (!getline(fs8, line)) - return 0; - - // Look for utf-8 byte-order mark at the beginning - if (line.size() > 2) { - if (utf8::is_bom(line.c_str())) - cout << "There is a byte order mark at the beginning of the file\n"; - } - - // Play with all the lines in the file - do { - // check for invalid utf-8 (for a simple yes/no check, there is also utf8::is_valid function) - string::iterator end_it = utf8::find_invalid(line.begin(), line.end()); - if (end_it != line.end()) { - cout << "Invalid UTF-8 encoding detected at line " << line_count << "\n"; - cout << "This part is fine: " << string(line.begin(), end_it) << "\n"; - } - // Get the line length (at least for the valid part) - int length = utf8::distance(line.begin(), end_it); - cout << "Length of line " << line_count << " is " << length << "\n"; - - // Convert it to utf-16 - vector utf16line; - utf8::utf8to16(line.begin(), end_it, back_inserter(utf16line)); - // And back to utf-8; - string utf8line; - utf8::utf16to8(utf16line.begin(), utf16line.end(), back_inserter(utf8line)); - // Confirm that the conversion went OK: - if (utf8line != string(line.begin(), end_it)) - cout << "Error in UTF-16 conversion at line: " << line_count << "\n"; - - getline(fs8, line); - line_count++; - } while (!fs8.eof()); - - return 0; -} diff --git a/v1_0/source/utf8.h b/v1_0/source/utf8.h deleted file mode 100644 index 82dc857..0000000 --- a/v1_0/source/utf8.h +++ /dev/null @@ -1,569 +0,0 @@ -// Copyright 2006 Nemanja Trifunovic - -/* -Permission is hereby granted, free of charge, to any person or organization -obtaining a copy of the software and accompanying documentation covered by -this license (the "Software") to use, reproduce, display, distribute, -execute, and transmit the Software, and to prepare derivative works of the -Software, and to permit third-parties to whom the Software is furnished to -do so, all subject to the following: - -The copyright notices in the Software and this entire statement, including -the above license grant, this restriction and the following disclaimer, -must be included in all copies of the Software, in whole or in part, and -all derivative works of the Software, unless such copies or derivative -works are solely in the form of machine-executable object code generated by -a source language processor. - -THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR -IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, -FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT -SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE -FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE, -ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER -DEALINGS IN THE SOFTWARE. -*/ - - -#ifndef UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731 -#define UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731 - -#include -#include - -namespace utf8 -{ - // The typedefs for 8-bit, 16-bit and 32-bit unsigned integers - // You may need to change them to match your system. - // These typedefs have the same names as ones from cstdint, or boost/cstdint - typedef unsigned char uint8_t; - typedef unsigned short uint16_t; - typedef unsigned int uint32_t; - - // Exceptions that may be thrown from the library functions. - class invalid_code_point : public std::exception { - uint32_t cp; - public: - invalid_code_point(uint32_t cp) : cp(cp) {} - virtual const char* what() const throw() { return "Invalid code point"; } - uint32_t code_point() const {return cp;} - }; - - class invalid_utf8 : public std::exception { - uint8_t u8; - public: - invalid_utf8 (uint8_t u) : u8(u) {} - virtual const char* what() const throw() { return "Invalid UTF-8"; } - uint8_t utf8_octet() const {return u8;} - }; - - class invalid_utf16 : public std::exception { - uint16_t u16; - public: - invalid_utf16 (uint16_t u) : u16(u) {} - virtual const char* what() const throw() { return "Invalid UTF-16"; } - uint16_t utf16_word() const {return u16;} - }; - - class not_enough_room : public std::exception { - public: - virtual const char* what() const throw() { return "Not enough space"; } - }; - - - -// Helper code - not intended to be directly called by the library users. May be changed at any time -namespace internal -{ - // Unicode constants - // Leading (high) surrogates: 0xd800 - 0xdbff - // Trailing (low) surrogates: 0xdc00 - 0xdfff - const uint16_t LEAD_SURROGATE_MIN = 0xd800u; - const uint16_t LEAD_SURROGATE_MAX = 0xdbffu; - const uint16_t TRAIL_SURROGATE_MIN = 0xdc00u; - const uint16_t TRAIL_SURROGATE_MAX = 0xdfffu; - const uint16_t LEAD_OFFSET = LEAD_SURROGATE_MIN - (0x10000 >> 10); - const uint32_t SURROGATE_OFFSET = 0x10000u - (LEAD_SURROGATE_MIN << 10) - TRAIL_SURROGATE_MIN; - - // Maximum valid value for a Unicode code point - const uint32_t CODE_POINT_MAX = 0x0010ffffu; - - template - inline uint8_t mask8(octet_type oc) - { - return static_cast(0xff & oc); - } - template - inline uint16_t mask16(u16_type oc) - { - return static_cast(0xffff & oc); - } - template - inline bool is_trail(octet_type oc) - { - return ((mask8(oc) >> 6) == 0x2); - } - - template - inline bool is_surrogate(u16 cp) - { - return (cp >= LEAD_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX); - } - - template - inline bool is_code_point_valid(u32 cp) - { - return (cp <= CODE_POINT_MAX && !is_surrogate(cp) && cp != 0xfffe && cp != 0xffff); - } - - template - inline typename std::iterator_traits::difference_type - sequence_length(octet_iterator lead_it) - { - uint8_t lead = mask8(*lead_it); - if (lead < 0x80) - return 1; - else if ((lead >> 5) == 0x6) - return 2; - else if ((lead >> 4) == 0xe) - return 3; - else if ((lead >> 3) == 0x1e) - return 4; - else - return 0; - } - - enum utf_error {OK, NOT_ENOUGH_ROOM, INVALID_LEAD, INCOMPLETE_SEQUENCE, OVERLONG_SEQUENCE, INVALID_CODE_POINT}; - - template - utf_error validate_next(octet_iterator& it, octet_iterator end, uint32_t* code_point = 0) - { - uint32_t cp = mask8(*it); - // Check the lead octet - typedef typename std::iterator_traits::difference_type octet_difference_type; - octet_difference_type length = sequence_length(it); - - // "Shortcut" for ASCII characters - if (length == 1) { - if (end - it > 0) { - if (code_point) - *code_point = cp; - ++it; - return OK; - } - else - return NOT_ENOUGH_ROOM; - } - - // Do we have enough memory? - if (end - it < length) - return NOT_ENOUGH_ROOM; - - // Check trail octets and calculate the code point - switch (length) { - case 0: - return INVALID_LEAD; - break; - case 2: - if (is_trail(*(++it))) { - cp = ((cp << 6) & 0x7ff) + ((*it) & 0x3f); - } - else { - --it; - return INCOMPLETE_SEQUENCE; - } - break; - case 3: - if (is_trail(*(++it))) { - cp = ((cp << 12) & 0xffff) + ((mask8(*it) << 6) & 0xfff); - if (is_trail(*(++it))) { - cp += (*it) & 0x3f; - } - else { - --it; --it; - return INCOMPLETE_SEQUENCE; - } - } - else { - --it; - return INCOMPLETE_SEQUENCE; - } - break; - case 4: - if (is_trail(*(++it))) { - cp = ((cp << 18) & 0x1fffff) + ((mask8(*it) << 12) & 0x3ffff); - if (is_trail(*(++it))) { - cp += (mask8(*it) << 6) & 0xfff; - if (is_trail(*(++it))) { - cp += (*it) & 0x3f; - } - else { - --it; --it; --it; - return INCOMPLETE_SEQUENCE; - } - } - else { - --it; --it; - return INCOMPLETE_SEQUENCE; - } - } - else { - --it; - return INCOMPLETE_SEQUENCE; - } - break; - } - // Is the code point valid? - if (!is_code_point_valid(cp)) { - for (octet_difference_type i = 0; i < length - 1; ++i) - --it; - return INVALID_CODE_POINT; - } - - if (code_point) - *code_point = cp; - - if (cp < 0x80) { - if (length != 1) { - for (octet_difference_type i = 0; i < length - 1; ++i) - --it; - return OVERLONG_SEQUENCE; - } - } - else if (cp < 0x800) { - if (length != 2) { - for (octet_difference_type i = 0; i < length - 1; ++i) - --it; - return OVERLONG_SEQUENCE; - } - } - else if (cp < 0x10000) { - if (length != 3) { - for (octet_difference_type i = 0; i < length - 1; ++i) - --it; - return OVERLONG_SEQUENCE; - } - } - - ++it; - return OK; - } - -} // namespace internal - - /// The library API - functions intended to be called by the users - - // Byte order mark - const uint8_t bom[] = {0xef, 0xbb, 0xbf}; - - template - octet_iterator find_invalid(octet_iterator start, octet_iterator end) - { - octet_iterator result = start; - while (result != end) { - internal::utf_error err_code = internal::validate_next(result, end); - if (err_code != internal::OK) - return result; - } - return result; - } - - template - bool is_valid(octet_iterator start, octet_iterator end) - { - return (find_invalid(start, end) == end); - } - - template - bool is_bom (octet_iterator it) - { - return ( - (internal::mask8(*it++)) == bom[0] && - (internal::mask8(*it++)) == bom[1] && - (internal::mask8(*it)) == bom[2] - ); - } - template - octet_iterator append(uint32_t cp, octet_iterator result) - { - if (!internal::is_code_point_valid(cp)) - throw invalid_code_point(cp); - - if (cp < 0x80) // one octet - *(result++) = static_cast(cp); - else if (cp < 0x800) { // two octets - *(result++) = static_cast((cp >> 6) | 0xc0); - *(result++) = static_cast((cp & 0x3f) | 0x80); - } - else if (cp < 0x10000) { // three octets - *(result++) = static_cast((cp >> 12) | 0xe0); - *(result++) = static_cast((cp >> 6) & 0x3f | 0x80); - *(result++) = static_cast((cp & 0x3f) | 0x80); - } - else if (cp <= internal::CODE_POINT_MAX) { // four octets - *(result++) = static_cast((cp >> 18) | 0xf0); - *(result++) = static_cast((cp >> 12)& 0x3f | 0x80); - *(result++) = static_cast((cp >> 6) & 0x3f | 0x80); - *(result++) = static_cast((cp & 0x3f) | 0x80); - } - else - throw invalid_code_point(cp); - - return result; - } - - template - uint32_t next(octet_iterator& it, octet_iterator end) - { - uint32_t cp = 0; - internal::utf_error err_code = internal::validate_next(it, end, &cp); - switch (err_code) { - case internal::OK : - break; - case internal::NOT_ENOUGH_ROOM : - throw not_enough_room(); - case internal::INVALID_LEAD : - case internal::INCOMPLETE_SEQUENCE : - case internal::OVERLONG_SEQUENCE : - throw invalid_utf8(*it); - case internal::INVALID_CODE_POINT : - throw invalid_code_point(cp); - } - return cp; - } - - template - uint32_t prior(octet_iterator& it, octet_iterator start) - { - octet_iterator end = it; - while (internal::is_trail(*(--it))) - if (it < start) - throw invalid_utf8(*it); // error - no lead byte in the sequence - octet_iterator temp = it; - return next(temp, end); - } - - /// Deprecated in versions that include "prior" - template - uint32_t previous(octet_iterator& it, octet_iterator pass_start) - { - octet_iterator end = it; - while (internal::is_trail(*(--it))) - if (it == pass_start) - throw invalid_utf8(*it); // error - no lead byte in the sequence - octet_iterator temp = it; - return next(temp, end); - } - - template - void advance (octet_iterator& it, distance_type n, octet_iterator end) - { - for (distance_type i = 0; i < n; ++i) - next(it, end); - } - - template - typename std::iterator_traits::difference_type - distance (octet_iterator first, octet_iterator last) - { - typename std::iterator_traits::difference_type dist; - for (dist = 0; first < last; ++dist) - next(first, last); - return dist; - } - - template - octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result) - { - while (start != end) { - uint32_t cp = internal::mask16(*start++); - // Take care of surrogate pairs first - if (internal::is_surrogate(cp)) { - if (start != end) { - uint32_t trail_surrogate = internal::mask16(*start++); - if (trail_surrogate >= internal::TRAIL_SURROGATE_MIN && trail_surrogate <= internal::TRAIL_SURROGATE_MAX) - cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET; - else - throw invalid_utf16(static_cast(trail_surrogate)); - } - else - throw invalid_utf16(static_cast(*start)); - - } - result = append(cp, result); - } - return result; - } - - template - u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result) - { - while (start != end) { - uint32_t cp = next(start, end); - if (cp > 0xffff) { //make a surrogate pair - *result++ = static_cast((cp >> 10) + internal::LEAD_OFFSET); - *result++ = static_cast((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN); - } - else - *result++ = static_cast(cp); - } - return result; - } - - template - octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result) - { - while (start != end) - result = append(*(start++), result); - - return result; - } - - template - u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result) - { - while (start < end) - (*result++) = next(start, end); - - return result; - } - - namespace unchecked - { - template - octet_iterator append(uint32_t cp, octet_iterator result) - { - if (cp < 0x80) // one octet - *(result++) = static_cast(cp); - else if (cp < 0x800) { // two octets - *(result++) = static_cast((cp >> 6) | 0xc0); - *(result++) = static_cast((cp & 0x3f) | 0x80); - } - else if (cp < 0x10000) { // three octets - *(result++) = static_cast((cp >> 12) | 0xe0); - *(result++) = static_cast((cp >> 6) & 0x3f | 0x80); - *(result++) = static_cast((cp & 0x3f) | 0x80); - } - else { // four octets - *(result++) = static_cast((cp >> 18) | 0xf0); - *(result++) = static_cast((cp >> 12)& 0x3f | 0x80); - *(result++) = static_cast((cp >> 6) & 0x3f | 0x80); - *(result++) = static_cast((cp & 0x3f) | 0x80); - } - return result; - } - template - uint32_t next(octet_iterator& it) - { - uint32_t cp = internal::mask8(*it); - typename std::iterator_traits::difference_type length = utf8::internal::sequence_length(it); - switch (length) { - case 1: - break; - case 2: - it++; - cp = ((cp << 6) & 0x7ff) + ((*it) & 0x3f); - break; - case 3: - ++it; - cp = ((cp << 12) & 0xffff) + ((internal::mask8(*it) << 6) & 0xfff); - ++it; - cp += (*it) & 0x3f; - break; - case 4: - ++it; - cp = ((cp << 18) & 0x1fffff) + ((internal::mask8(*it) << 12) & 0x3ffff); - ++it; - cp += (internal::mask8(*it) << 6) & 0xfff; - ++it; - cp += (*it) & 0x3f; - break; - } - ++it; - return cp; - } - - template - uint32_t prior(octet_iterator& it) - { - while (internal::is_trail(*(--it))) ; - octet_iterator temp = it; - return next(temp); - } - - // Deprecated in versions that include prior, but only for the sake of consistency (see utf8::previous) - template - inline uint32_t previous(octet_iterator& it) - { - return prior(it); - } - - template - void advance (octet_iterator& it, distance_type n) - { - for (distance_type i = 0; i < n; ++i) - next(it); - } - - template - typename std::iterator_traits::difference_type - distance (octet_iterator first, octet_iterator last) - { - typename std::iterator_traits::difference_type dist; - for (dist = 0; first < last; ++dist) - next(first); - return dist; - } - - template - octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result) - { - while (start != end) { - uint32_t cp = internal::mask16(*start++); - // Take care of surrogate pairs first - if (internal::is_surrogate(cp)) { - uint32_t trail_surrogate = internal::mask16(*start++); - cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET; - } - result = append(cp, result); - } - return result; - } - - template - u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result) - { - while (start != end) { - uint32_t cp = next(start); - if (cp > 0xffff) { //make a surrogate pair - *result++ = static_cast((cp >> 10) + internal::LEAD_OFFSET); - *result++ = static_cast((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN); - } - else - *result++ = static_cast(cp); - } - return result; - } - - template - octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result) - { - while (start != end) - result = append(*(start++), result); - - return result; - } - - template - u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result) - { - while (start < end) - (*result++) = next(start); - - return result; - } - - } // namespace utf8::unchecked -} // namespace utf8 - -#endif // header guard diff --git a/v1_0/test_data/negative/utf8_invalid.txt b/v1_0/test_data/negative/utf8_invalid.txt deleted file mode 100755 index abd16f7253bf7254ad1ae04cb5bee8d8c47e407a..0000000000000000000000000000000000000000 GIT binary patch literal 0 HcmV?d00001 literal 20334 zcmdU1X>%Ocb-l=P@_l?QkaQ+KqMb=kWH&#~HSJo~$&h?IO#*?-m zc%Ubgju-S~81=~ARry~yhNh5G^057n(4B1 z-Jl)CU9Yt)Q7lo~@#2A>c;bht2ToHz+%uR?;yu;(!lswhMM+X>Kw223()HXhl{Auu zCoaH4V!C)(1yz@8sk9={!DoAbZN`2Bgt*~QdTyNh&3@ow^nTimx?SUnX>wt*17rPAz z)GE5+b=(6;DHb=Cgmm-*H)9tx`CZcBhe_(WATM%qC1CJyU)%=BH>6_>9koDo+V zLQs$lfz)-uJLDAvP==4s@nApfCw(`-P`!Q%VP8G$d9hE)gDPo5PL>ZR?SRy7gyGtL zoTMwMPwDl+c&u6;Glm2YL9lou@LaqSg&uTj?4lP(5Cu4-)I2{fgff(VLK{#CQ{{D9 zq|vJcu)PF24`6-G=m6dVA%rbA9?}L{K3PgiHa2NV;wCcif`C6WiwuSWR^fTA%#?Gp zqik-3KEK1mEzjviFjCkwg^)nkK}$j?9(L4hLW|&qrl@wFVP*6`)WpXvfwh*ek+1J39Sl`y({PyUv>iuXYRwo~Fm!U$wRSqC&$svCdeo15fXJl* zDAN*bHU{fXI|Ba=#F8QyxBDb2@b=tbJhqjLR|9PLK+X9_%WELc>HrMiEx+An zd`GTfTxa@1{9y!DbA#~0HbP7kBCx!TkqH*o@tV-ypyR+x5smqBvafgZ2u0L{Bu0Fm~gU2Wn0TThEIHF!8 zzGf+Cnr4)EG$9vi)68YFWHWY?4r34!B#VxQCTZ)OSr~Q$L^vh}r|BX}2=X}f-1K5< z`5{<}$s9@rByf31d8rq$fI*bvyH4BlTIY;;w@jjedU9Y7iedni z+NcJPIc$18vh~)RzPp+g1|5eS9F9dx>?kmdP#0`5x@!@kpZ= zvO3BFgbO!-LxpgI1L)2qDg;pa8|a%JQ1cS1vlvFr{0fW!#_b9mtBur7r)kn4RG~}s zX>g_mU*e~Ib+<$-$WoPf4i5x<9TX(w@kYorUT>iuXt8K(3_&}{D#fha9c^Nrk>zr; zF;T@>4W=6K@x3ANow5%u(~3jH0u7cL&grU|38{rZiq0b}o3)-+qlYmhm*vFQ$T{(= zGhZAzYa&mw%Cbevv?*#tUSS3FcF7H_+Z z_tB%OfFlLm5ZRaj+#VzF_A_%LZi;M+b;O9E6T*>$Ja7J5ctctfCfR-EtP@4TGFv-dnpR^Zv4`)+pq6mU(aO zmhoP`Srt$PSf4g;%=pTHcW=&#IBDK%1S}(d^5(pd6Xw04h-Ju60dh_<$ITl;)T^YK zPZM(v(9;_9`1{ljbn^u2hnXuo<4@oJx3e(s4Vt$JvO5r3Q5pRg-$@VJ$0r3;nqfH4BQZ$HA@D34`z($LRcW=H>)m=)6uy7)-taQ^BX8G(@Zw}*M27&(yPV>4zK^MI6| zJp=mG5|Wf4|$s(|46qmHsjG*=iRngNcV_d9%P^7C!>6 ztZ>=QUZWXPJ=SwRR%D|=Shvqr{keF45gDivQ+rM+Lsk#BS1(JgYV82~GnJht`)TC@ zuh9lx)p&C@{K7}pr)k5yuXa?GuuNfwUqqRWd*M};oB=d=2r--Y#G8vkgNFoq;of-j zP-yVBSZ_|*ijm*Z&3R;K@U}&^j>D@?;n~>BCCtI?1_f6wuz+@PvnXY!B_T`nn-v;+ zQKnGCi>D8uwWBZpil^W4m0$JFcYXEOeC^kL{WrYZ*wRVR0nJ4SU^is?An&s2FC}l@Y|Wt$9T`x<&AZ-A)2LK zSoZpguFTn$2TaUY51X{(RvYX3Gp?LIUEwp!a>#+YHzZ*03>rubnn_9oO<>T@<^0)GL z^7rx&@{jUQ^3U=w@~`r5az{QPcmLn@fqH}b*q&6!<_vYTsgCy6YRsw%Dji*%rH>}{(Rx$s<8}G;0(3#0oP|CRt!%Z6ZA)$s>;Cstl`CBzI~CY-KIU3H zeKZsnDcZTEO)c2G!zLd#6m8j3o}p_`LOw0ewp0s(XU)$|kAZIJTO{smX)_P|WTrYI z3OMK^-wD=@U@j)0uHx1rmK0L7Q0b-oCODBBD+0bUz3ym8M980r?iCSV zo3U|XAQ81D0#rrF*Jo|U7);F6D{IDV!I?dU+RL*AiJ5w3%_tt%Nik)`a_ekBOw}uE zh6}I6Q$TDb%tplIy0T_gR*MaV8g~+AL&D1{Yi6aipHS0{glWv&9T###O~V`?MyC(f z4%x9`dNh1AbWTLFq{@Jcj}eTq3|Ww)jj0-L;p<$c$;f6m78)+fF%mBnohFv{QQq3Y zUMD7ue6h6BoY3OfpNr=g$hBLyj}ScQ?dqN{-@OTorHRe72}?`WpNpqiHzKZe^Zitl z6RXlQ`P|~^yAJy)n*Z2LW++5wqxN<7dLFt>k@oV&P}>2RYTM;Fg^Q;T@?#!sd)!=l zW76lxN5B7X^yv$nceiz4=`)MLLmC8q{MXKa-+1FQC&FI5{1CyOK%1L39Tq|2{*s#g z#Nz22x4(iy+xT6?DYUs2eeMip~*h@CpAcUnBI^x(SXYT-MHE98BRk z4((Le#$`6N2keSR?n3d}79MMuumwuOUL!rzffZ5P4od<3vQm zGmWv@9cl>30HKdalAfNE(K8td4tQX^tdA4rHLB{1+k#3ps(CMnKv%ZCQDm7 zn|hK0^7NZLGlbP%YzXGp$kDcc5ZM^=6b@Dz*q+JuQ8a97=eC(pQ21H5Y(5{T%Pu}0 zyG9O=)bOYfPgrCnqHUvRqbZ^U1iSR;?m0Bx=@}2m1{6Vn+Qbj@D+7+Ss~5?<&jU;u zRs02co`)7z4_9$^fYU5!0ZsPk5H+x9_~!(y#HzxM&;%OM(2aIoZGJU0aVh?6bbJY8aFncccZGiC43nemQ<500s#YGe<=* zr^QJqYC;W)1)6t=lO33(=GWrm^Cq+JRUFL2+}+OQb7Chnl9O@Io5j=jMO^rRXo^^y zN!v8gLr>IkQQ@@NcbzjZNodJlikL!xNlp{2wRB{ucD{yQYI9l(c4w3c-?A6|mxp>v z<@UIOmsPRynbPSus|+vtg|twiQ@^Sd=Cmy7T$Wkave8v2)JGVdfF3I#suK) zqj?cG3dFYUGRi@Lh&ju=keemQ?W|=By-Nlakema}i+Q1h*(@*(EHHIWH4o_gCUV>x z)DDXC$J|4|+wT@`S|o+z-k$z$@#c6%PlxJs8ji-u(80+S9!;@_IZ-k7`3({lYDANV zaR3TO#u%|VkqUD{M@}AzEQ>7C$~jBjpX2NyaG^}ikFsbE%g#huK$IWsYRZqT>X{j4 zkZCVR*5LAihQp$kv#~4#969BnHc^?52eNV&vgAztT)aMDFHBIT9g#QK?V}Q&(x%qf|3aJy!XH#mf)+Rd+TA5jEW-Ht! zXA5Z3eHjygx2Ja_$|&V~gGhI_h?hPs+neOMrq&w%B$Kv(DrQj#c#x7|>;}oXpakPi^i83Q4o{qac6Z%Z}+QES~ zI2c!1bT$BAyYozCN6U$ZhnP0)8xQVW(b|TH=-bmoeCOFpSvW`IjX~7-wR1&-01@>> z2x)xoq%>;y+PR{Y2obepAmZ~UrBQ>|&cjxYja-iJJ1LFWw1pgZE!Xf{69wa!?h1Q=rx^sWU zE6*n1Tg+TJ1!iuWz`Vbr3})sr@WC-U)fLC+eD-E#Iy0X!m<63VW==W9D=MvkIN3 zcEK?K+R;XK`q2I@mD3bGXOX?K;v2HN%Iu{ALzqNFyL=9%@8$v a&2b9W0wR0mw+p!$IoY3(SqK`l>;D0Y6_gYJ diff --git a/v1_0/test_data/utf8samples/UTF-8-demo.txt b/v1_0/test_data/utf8samples/UTF-8-demo.txt deleted file mode 100644 index 4363f27..0000000 --- a/v1_0/test_data/utf8samples/UTF-8-demo.txt +++ /dev/null @@ -1,212 +0,0 @@ - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ diff --git a/v1_0/test_data/utf8samples/Unicode_transcriptions.html b/v1_0/test_data/utf8samples/Unicode_transcriptions.html deleted file mode 100644 index 69b29ff..0000000 --- a/v1_0/test_data/utf8samples/Unicode_transcriptions.html +++ /dev/null @@ -1,167 +0,0 @@ -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - diff --git a/v1_0/test_data/utf8samples/big.txt b/v1_0/test_data/utf8samples/big.txt deleted file mode 100644 index 1038482..0000000 --- a/v1_0/test_data/utf8samples/big.txt +++ /dev/null @@ -1,420160 +0,0 @@ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ diff --git a/v1_0/test_data/utf8samples/quickbrown.txt b/v1_0/test_data/utf8samples/quickbrown.txt deleted file mode 100644 index 5db9443..0000000 --- a/v1_0/test_data/utf8samples/quickbrown.txt +++ /dev/null @@ -1,126 +0,0 @@ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. diff --git a/v1_0/test_drivers/Makefile b/v1_0/test_drivers/Makefile deleted file mode 100644 index a2cbe4c..0000000 --- a/v1_0/test_drivers/Makefile +++ /dev/null @@ -1,19 +0,0 @@ -CC = g++ -CFLAGS = -g - -all: smoketest regressiontest negativetest utf8readertest - -smoketest: - cd smoke_test && $(MAKE) $@ - -regressiontest: - cd regression_tests && $(MAKE) $@ - -negativetest: - cd negative && $(MAKE) $@ - -utf8readertest: - cd utf8reader && $(MAKE) $@ - -clean: - rm smoke_test/smoketest regression_tests/regressiontest negative/negative utf8reader/utf8reader diff --git a/v1_0/test_drivers/negative/Makefile b/v1_0/test_drivers/negative/Makefile deleted file mode 100644 index 02159f7..0000000 --- a/v1_0/test_drivers/negative/Makefile +++ /dev/null @@ -1,5 +0,0 @@ -CC = g++ -CFLAGS = -g -Wall -pedantic - -negativetest: negative.cpp ../../source/utf8.h - $(CC) $(CFLAGS) negative.cpp -onegative diff --git a/v1_0/test_drivers/negative/negative.cpp b/v1_0/test_drivers/negative/negative.cpp deleted file mode 100644 index 571e6c6..0000000 --- a/v1_0/test_drivers/negative/negative.cpp +++ /dev/null @@ -1,39 +0,0 @@ -#include "../../source/utf8.h" -using namespace utf8; - -#include -#include -#include -#include -using namespace std; - -const char* TEST_FILE_PATH = "../../test_data/negative/utf8_invalid.txt"; -const unsigned INVALID_LINES[] = { 75, 76, 82, 83, 84, 85, 93, 102, 103, 105, 106, 107, 108, 109, 110, 114, 115, 116, 117, 124, 125, 130, 135, 140, 145, 153, 154, 155, 156, 157, 158, 159, 160, 161, 162, 169, 175, 176, 177, 207, 208, 209, 210, 211, 220, 221, 222, 223, 224, 232, 233, 234, 235, 236, 247, 248, 249, 250, 251, 252, 253, 257, 258, 259, 260, 261, 262, 263, 264, 268, 269}; -const unsigned* INVALID_LINES_END = INVALID_LINES + sizeof(INVALID_LINES)/sizeof(unsigned); - -int main() -{ - // Open the test file - ifstream fs8(TEST_FILE_PATH); - if (!fs8.is_open()) { - cout << "Could not open " << TEST_FILE_PATH << endl; - return 0; - } - - // Read it line by line - unsigned int line_count = 0; - char byte; - while (!fs8.eof()) { - string line; - while ((byte = static_cast(fs8.get())) != '\n' && !fs8.eof()) - line.push_back(byte); - - line_count++; - // Print out lines that contain invalid UTF-8 - if (!is_valid(line.begin(), line.end())) { - const unsigned* u = find(INVALID_LINES, INVALID_LINES_END, line_count); - if (u == INVALID_LINES_END) - cout << "Unexpected invalid utf-8 at line " << line_count << '\n'; - } - } -} diff --git a/v1_0/test_drivers/performance/Makefile b/v1_0/test_drivers/performance/Makefile deleted file mode 100644 index d6d6214..0000000 --- a/v1_0/test_drivers/performance/Makefile +++ /dev/null @@ -1,5 +0,0 @@ -CC = g++ -CFLAGS = -O2 - -iconvtest: iconvtest.cpp ../../source/utf8.h timer.h - $(CC) $(CFLAGS) iconvtest.cpp -oiconvtest diff --git a/v1_0/test_drivers/performance/iconvtest.cpp b/v1_0/test_drivers/performance/iconvtest.cpp deleted file mode 100644 index 2f1c27c..0000000 --- a/v1_0/test_drivers/performance/iconvtest.cpp +++ /dev/null @@ -1,125 +0,0 @@ -#include -#include "../../source/utf8.h" -#include "timer.h" -#include -#include -#include -using namespace std; - -using namespace utf8; - -int main(int argc, char** argv) -{ - if (argc != 2) { - cout << "\nUsage: iconvtest filename\n"; - return 0; - } - const char* test_file_path = argv[1]; - // Open the test file (UTF-8 encoded text) - ifstream fs8(test_file_path, ios::binary); - if (!fs8.is_open()) { - cout << "Could not open " << test_file_path << endl; - return 0; - } - // get length - fs8.seekg(0, ios::end); - int length = fs8.tellg(); - fs8.seekg(0, ios::beg); - - // allocate the buffer (no vector - we are benchmarking conversions, not STL - char* buf = new char[length]; - char* end_buf = buf + length; - // fill the data - fs8.read(buf, length); - fs8.close(); - // the UTF-16 result will not be larger than this (I hope :) ) - vector temputf16; - utf8::utf8to16(buf, end_buf, back_inserter(temputf16)); - int wlength = temputf16.size(); - unsigned short* utf16buf = new unsigned short[wlength]; - - cout << "UTF8 to UTF-16\n"; - { - memset (utf16buf, 0 , wlength * sizeof(unsigned short)); - // utf-8 cpp: - cout << "utf8::utf8to16: "; - timer t(cout); - utf8::utf8to16(buf, buf + length, utf16buf); - } - - { - memset (utf16buf, 0 , wlength * sizeof(unsigned short)); - // utf-8 cpp: - cout << "unchecked::utf8to16: "; - timer t(cout); - utf8::unchecked::utf8to16(buf, buf + length, utf16buf); - } - - // the UTF-16 result will not be larger than this (I hope :) ) - unsigned short* utf16iconvbuf = new unsigned short[wlength]; - { - memset (utf16iconvbuf, 0 , wlength * sizeof(unsigned short)); - // iconv - cout << "iconv: "; - - iconv_t cd = iconv_open("UTF-16LE", "UTF-8"); - if (cd == iconv_t(-1)) { - cout << "Error openning the iconv stream"; - return 0; - } - char* inbuf = buf; - size_t in_bytes_left = length; - char* outbuf = (char*)utf16iconvbuf; - size_t out_bytes_left = wlength * sizeof (unsigned short); - { - timer t(cout); - iconv(cd, &inbuf, &in_bytes_left, &outbuf, &out_bytes_left); - } - iconv_close(cd); - } - - // just check the correctness while we are here: - if (!equal(utf16buf, utf16buf + wlength, utf16iconvbuf)) - cout << "Different result!!!\n"; - - // the other way around - cout << "UTF16 to UTF-8\n"; - { - //iconv - memset(buf, 0, length); - cout<< "iconv: "; - - iconv_t cd = iconv_open("UTF-8", "UTF-16LE"); - if (cd == iconv_t(-1)) { - cout << "Error openning the iconv stream"; - return 0; - } - char* inbuf = (char*)utf16buf; - size_t in_bytes_left = wlength * sizeof(unsigned short); - char* outbuf =buf; - size_t out_bytes_left = length; - { - timer t(cout); - iconv(cd, &inbuf, &in_bytes_left, &outbuf, &out_bytes_left); - } - iconv_close(cd); - } - - { - memset (buf, 0 , length); - // utf-8 cpp: - cout << "unchecked::utf16to8: "; - timer t(cout); - utf8::unchecked::utf16to8(utf16buf, utf16buf + wlength, buf); - } - - { - memset (buf, 0 , length); - cout << "utf16to8: "; - timer t(cout); - utf8::utf16to8(utf16buf, utf16buf + wlength, buf); - } - - delete [] buf; - delete [] utf16buf; -} diff --git a/v1_0/test_drivers/performance/timer.h b/v1_0/test_drivers/performance/timer.h deleted file mode 100644 index 170dea3..0000000 --- a/v1_0/test_drivers/performance/timer.h +++ /dev/null @@ -1,21 +0,0 @@ -#include -#include -struct timer { - timer(std::ostream& report) : report(report) - {start = std::clock();} - ~timer() - { - using namespace std; - end = clock(); - unsigned milliseconds = (end - start)*1000 / CLOCKS_PER_SEC; - report << "Spent " << milliseconds << "ms here\n"; - } - - std::clock_t start; - std::clock_t end; - std::ostream& report; - -private: - // just to surpress a VC++ 8.0 warning - timer& operator = (const timer&) {}; -}; diff --git a/v1_0/test_drivers/performance/win32.cpp b/v1_0/test_drivers/performance/win32.cpp deleted file mode 100644 index 9577920..0000000 --- a/v1_0/test_drivers/performance/win32.cpp +++ /dev/null @@ -1,105 +0,0 @@ -#include -#include "../../source/utf8.h" -#include "timer.h" -#include -#include -#include -using namespace std; - -using namespace utf8; - -int main(int argc, char** argv) -{ - if (argc != 2) { - cout << "\nUsage: win32test filename\n"; - return 0; - } - const char* test_file_path = argv[1]; - // Open the test file (UTF-8 encoded text) - ifstream fs8(test_file_path, ios::binary); - if (!fs8.is_open()) { - cout << "Could not open " << test_file_path << endl; - return 0; - } - // get length - fs8.seekg(0, ios::end); - int length = fs8.tellg(); - fs8.seekg(0, ios::beg); - - // allocate the buffer (no vector - we are benchmarking conversions, not STL - char* buf = new char[length]; - // fill the data - fs8.read(buf, length); - fs8.close(); - cout << "UTF8 > UTF16\n"; - // the UTF-16 result will not be larger than this (I hope :) ) - vector temputf16; - utf8::utf8to16(buf, buf + length, back_inserter(temputf16)); - vector::size_type wlength = temputf16.size(); - wchar_t* utf16buf = new wchar_t[wlength]; - - { - memset (utf16buf, 0 , wlength * sizeof(wchar_t)); - // utf-8 cpp: - cout << "utf8::utf8to16: "; - timer t(cout); - utf8::utf8to16(buf, buf + length, utf16buf); - } - - { - memset (utf16buf, 0 , wlength * sizeof(wchar_t)); - // utf-8 cpp: - cout << "unchecked::utf8to16: "; - timer t(cout); - utf8::unchecked::utf8to16(buf, buf + length, utf16buf); - } - - // the UTF-16 result will not be larger than this (I hope :) ) - wchar_t* utf16iconvbuf = new wchar_t[wlength]; - { - memset (utf16iconvbuf, 0 , wlength * sizeof(wchar_t)); - // win32 - cout << "win32: "; - - { - timer t(cout); - MultiByteToWideChar(CP_UTF8, MB_ERR_INVALID_CHARS, buf, length, utf16iconvbuf, int(wlength)); - } - - } - - // just check the correctness while we are here: - if (!equal(utf16buf, utf16buf + wlength, utf16iconvbuf)) - cout << "Different result!!!"; - - // the other way around - cout << "UTF16 to UTF-8\n"; - { - //win32 - memset(buf, 0, length); - cout<< "win32: "; - - { - timer t(cout); - WideCharToMultiByte(CP_UTF8, 0, utf16buf, int(wlength), buf, length, NULL, NULL); - } - } - - { - memset (buf, 0 , length); - // utf-8 cpp: - cout << "unchecked::utf16to8: "; - timer t(cout); - utf8::unchecked::utf16to8(utf16buf, utf16buf + wlength, buf); - } - - { - memset (buf, 0 , length); - cout << "utf16to8: "; - timer t(cout); - utf8::utf16to8(utf16buf, utf16buf + wlength, buf); - } - - delete [] buf; - delete [] utf16buf; -} diff --git a/v1_0/test_drivers/regression_tests/Makefile b/v1_0/test_drivers/regression_tests/Makefile deleted file mode 100644 index 03f8cfe..0000000 --- a/v1_0/test_drivers/regression_tests/Makefile +++ /dev/null @@ -1,6 +0,0 @@ -CC = g++ -CFLAGS = -g -Wall -pedantic -REG_FILES = r1_0Beta1/*h r1_0Beta2/*.h - -regressiontest: reg_tests_driver.cpp ../../source/utf8.h $(REG_FILES) - $(CC) $(CFLAGS) reg_tests_driver.cpp -o regressiontest diff --git a/v1_0/test_drivers/regression_tests/r1_0Beta1/basic_functionality.h b/v1_0/test_drivers/regression_tests/r1_0Beta1/basic_functionality.h deleted file mode 100644 index 15c45ce..0000000 --- a/v1_0/test_drivers/regression_tests/r1_0Beta1/basic_functionality.h +++ /dev/null @@ -1,16 +0,0 @@ -#include "../../../source/utf8.h" -using namespace utf8; - -// [ 1528544 ] utf::next does not work correctly for 4-byte sequences -void id_1528544() -{ - unsigned char u10ffff[] = {0xf4, 0x8f, 0xbf, 0xbf}; - unsigned char* uit = u10ffff; - try { - unsigned int cp_u10ffff = next (uit, u10ffff + 4); - check (cp_u10ffff == 0x10ffff); - } - catch (std::exception&) { - check (false); - } -} diff --git a/v1_0/test_drivers/regression_tests/r1_0Beta1/invalidutf8.h b/v1_0/test_drivers/regression_tests/r1_0Beta1/invalidutf8.h deleted file mode 100644 index f284a9c..0000000 --- a/v1_0/test_drivers/regression_tests/r1_0Beta1/invalidutf8.h +++ /dev/null @@ -1,96 +0,0 @@ -#include "../../../source/utf8.h" -using namespace utf8; - -/// [ 1524459 ] utf8::is_valid does not report some illegal code positions -void id_1524459() -{ -// Single UTF-16 surrogates: -unsigned char ud800[] = {0xed, 0xa0, 0x80}; -check (!is_valid(ud800, ud800 + 3)); - -unsigned char udb7f[] = {0xed, 0xad, 0xbf}; -check (!is_valid(udb7f, udb7f + 3)); - -unsigned char udb80[] = {0xed, 0xae, 0x80}; -check (!is_valid(udb80, udb80 + 3)); - -unsigned char udbff[] = {0xed, 0xaf, 0xbf}; -check (!is_valid(udbff, udbff + 3)); - -unsigned char udc00[] = {0xed, 0xb0, 0x80}; -check (!is_valid(udc00, udc00 + 3)); - -unsigned char udf80[] = {0xed, 0xbe, 0x80}; -check (!is_valid(udf80, udf80 + 3)); - -unsigned char udfff[] = {0xed, 0xbf, 0xbf}; -check (!is_valid(udfff, udfff + 3)); - -// Paired UTF-16 surrogates: -unsigned char ud800_dc00[] = {0xed, 0xa0, 0x80, 0xed, 0xb0, 0x80}; -check (!is_valid(ud800_dc00, ud800_dc00 + 6)); - -unsigned char ud800_dfff[] = {0xed, 0xa0, 0x80, 0xed, 0xbf, 0xbf}; -check (!is_valid(ud800_dfff, ud800_dfff + 6)); - -unsigned char udb7f_dc00[] = {0xed, 0xad, 0xbf, 0xed, 0xb0, 0x80}; -check (!is_valid(udb7f_dc00, udb7f_dc00 + 6)); - -unsigned char udb7f_dfff[] = {0xed, 0xad, 0xbf, 0xed, 0xbf, 0xbf}; -check (!is_valid(udb7f_dfff, udb7f_dfff + 6)); - -unsigned char udb80_dc00[] = {0xed, 0xae, 0x80, 0xed, 0xb0, 0x80}; -check (!is_valid(udb80_dc00, udb80_dc00 + 6)); - -unsigned char udb80_dfff[] = {0xed, 0xae, 0x80, 0xed, 0xbf, 0xbf}; -check (!is_valid(udb80_dfff, udb80_dfff + 6)); - -unsigned char udbff_dc00[] = {0xed, 0xaf, 0xbf, 0xed, 0xb0, 0x80}; -check (!is_valid(udbff_dc00, udbff_dc00 + 6)); - -unsigned char udbff_dfff[] = {0xed, 0xaf, 0xbf, 0xed, 0xbf, 0xbf}; -check (!is_valid(udbff_dfff, udbff_dfff + 6)); - -// Other illegal code points -unsigned char ufffe[] = {0xef, 0xbf, 0xbe}; -check (!is_valid(ufffe, ufffe + 3)); - -unsigned char uffff[] = {0xef, 0xbf, 0xbf}; -check (!is_valid(uffff, uffff + 3)); -} - -// [ 1525236 ] utf8::is_valid does not detect overlong sequences -void id_1525236 () -{ -unsigned char u2f_2bytes[] = {0xc0, 0xaf}; -check (!is_valid(u2f_2bytes, u2f_2bytes + 2)); - -unsigned char u2f_3bytes[] = {0xe0, 0x80, 0xaf}; -check (!is_valid(u2f_3bytes, u2f_3bytes + 3)); - -unsigned char u2f_4bytes[] = {0xf0, 0x80, 0x80, 0xaf}; -check (!is_valid(u2f_4bytes, u2f_4bytes + 4)); -} - -// [ 1528369 ] utf8::find_invalid does not return the start of a seqence -void id_1528369 () -{ -// incomplete utf sequences -unsigned char utf_incomplete[] = {0xe6, 0x97, 0x0}; -unsigned char* invalid = find_invalid(utf_incomplete, utf_incomplete + 3); -check (invalid == utf_incomplete); - -unsigned char utf_incomplete_two_seqs[] = {0xE6, 0x97, 0xA5, 0xd1, 0x0}; -invalid = find_invalid(utf_incomplete_two_seqs, utf_incomplete_two_seqs + 5); -check (invalid == utf_incomplete_two_seqs + 3); - -// invalid code point -unsigned char udbff[] = {0xed, 0xaf, 0xbf}; -invalid = find_invalid(udbff, udbff + 3); -check (invalid == udbff); - -// overlong sequence -unsigned char u2f_3bytes[] = {0xe0, 0x80, 0xaf}; -invalid = find_invalid(u2f_3bytes, u2f_3bytes + 3); -check (invalid == u2f_3bytes); -} diff --git a/v1_0/test_drivers/regression_tests/r1_0Beta2/basic_functionality.h b/v1_0/test_drivers/regression_tests/r1_0Beta2/basic_functionality.h deleted file mode 100644 index e5b65c5..0000000 --- a/v1_0/test_drivers/regression_tests/r1_0Beta2/basic_functionality.h +++ /dev/null @@ -1,11 +0,0 @@ -#include "../../../source/utf8.h" -using namespace utf8; - -// [ 1531740 ] utf8::append does not work correctly for some code points. -void id_1531740() -{ - unsigned cp_u3044 = 0x3044U; - unsigned char u3044[] = {0x0, 0x0, 0x0, 0x0}; - append(cp_u3044, u3044); - check (u3044[0] == 0xe3 && u3044[1] == 0x81 && u3044[2] == 0x84 && u3044[3] == 0); -} diff --git a/v1_0/test_drivers/regression_tests/r1_0Beta3/basic_functionality.h b/v1_0/test_drivers/regression_tests/r1_0Beta3/basic_functionality.h deleted file mode 100644 index 40af658..0000000 --- a/v1_0/test_drivers/regression_tests/r1_0Beta3/basic_functionality.h +++ /dev/null @@ -1,11 +0,0 @@ -#include "../../../source/utf8.h" -using namespace utf8; - -// [ 1538338 ] unchecked::next does not work correctly for 4-byte sequences. -void id_1538338() -{ - char* four_bytes = "\xf0\x90\x8d\x86"; - char* it = four_bytes; - int cp = unchecked::next(it); - check (cp == 0x10346); -} diff --git a/v1_0/test_drivers/regression_tests/reg_tests_driver.cpp b/v1_0/test_drivers/regression_tests/reg_tests_driver.cpp deleted file mode 100644 index 19a5ac3..0000000 --- a/v1_0/test_drivers/regression_tests/reg_tests_driver.cpp +++ /dev/null @@ -1,40 +0,0 @@ -#include -using namespace std; - -inline void check_impl (bool condition, const char* file, int line) - { - if (!condition) { - cout << "Check Failed! File: " << file << " Line: " << line << '\n'; - } - } - -#define check(c) check_impl(c, __FILE__, __LINE__); - -// Release 1.0 Beta 1 -#include "r1_0Beta1/invalidutf8.h" -#include "r1_0Beta1/basic_functionality.h" -// Release 1.0 Beta 2 -#include "r1_0Beta2/basic_functionality.h" -// Release 1.0 Beta 3 -#include "r1_0Beta3/basic_functionality.h" - - - -int main() -{ -// Release 1.0 Beta 1 -//r1_0Beta1/invalidutf8.h - id_1524459(); - id_1525236(); - id_1528369(); -//r1_0Beta1/basic_functionality.h - id_1528544(); - -// Release 1.0 Beta 2 -//r1_0Beta2/basic_functionality.h - id_1531740(); - -// Release 1.0 Beta 3 -//r1_0Beta3/basic_functionality.h - id_1538338(); -} diff --git a/v1_0/test_drivers/runtests.pl b/v1_0/test_drivers/runtests.pl deleted file mode 100755 index 77b5402..0000000 --- a/v1_0/test_drivers/runtests.pl +++ /dev/null @@ -1,50 +0,0 @@ -#! /usr/bin/perl - -$report_name = './report.txt'; - -# Create the report file -die if !open(REPORT, ">$report_name"); - -# First, build everything -print REPORT "==================Make output==================\n"; -close($report_name); - -`make >> $report_name`; -die if !open(REPORT, ">>$report_name"); -print REPORT "==================End of Make output==================\n"; -print REPORT "\n"; -# Now, run individual tests and create the report -print REPORT "==================Smoke Test ==================\n"; -close($report_name); -chdir 'smoke_test'; -`./smoketest >> ../$report_name`; -chdir '..'; -die if !open(REPORT, ">>$report_name"); -print REPORT "==================End of smoke test==================\n"; -print REPORT "\n"; -print REPORT "==================Regression Test ==================\n"; -close($report_name); -chdir 'regression_tests'; -`./regressiontest >> ../$report_name`; -chdir '..'; -die if !open(REPORT, ">>$report_name"); -print REPORT "==================End of regression test==================\n"; -print REPORT "\n"; -print REPORT "==================Negative Test ==================\n"; -close($report_name); -chdir 'negative'; -`./negative >> ../$report_name`; -chdir '..'; -die if !open(REPORT, ">>$report_name"); -print REPORT "==================End of negative test==================\n"; -print REPORT "\n"; -print REPORT "==================utf8reader runs ==================\n"; -close($report_name); -chdir 'utf8reader'; -`./utf8reader ../../test_data/utf8samples/quickbrown.txt >> ../$report_name`; -`./utf8reader ../../test_data/utf8samples/Unicode_transcriptions.html >> ../$report_name`; -`./utf8reader ../../test_data/utf8samples/UTF-8-demo.txt >> ../$report_name`; -chdir '..'; -die if !open(REPORT, ">>$report_name"); -print REPORT "==================End of utf8reader runs==================\n"; -print REPORT "\n"; diff --git a/v1_0/test_drivers/smoke_test/Makefile b/v1_0/test_drivers/smoke_test/Makefile deleted file mode 100644 index 11ec8e7..0000000 --- a/v1_0/test_drivers/smoke_test/Makefile +++ /dev/null @@ -1,5 +0,0 @@ -CC = g++ -CFLAGS = -g -Wall - -smoketest: test.cpp ../../source/utf8.h - $(CC) $(CFLAGS) test.cpp -osmoketest diff --git a/v1_0/test_drivers/smoke_test/test.cpp b/v1_0/test_drivers/smoke_test/test.cpp deleted file mode 100644 index e0e0646..0000000 --- a/v1_0/test_drivers/smoke_test/test.cpp +++ /dev/null @@ -1,235 +0,0 @@ - -#include -#include -#include -#include "../../source/utf8.h" -using namespace utf8; -using namespace std; - -int main() -{ - //append - unsigned char u[5] = {0,0,0,0,0}; - - unsigned char* end = append(0x0448, u); - assert (u[0] == 0xd1 && u[1] == 0x88 && u[2] == 0 && u[3] == 0 && u[4] == 0); - - end = append(0x65e5, u); - assert (u[0] == 0xe6 && u[1] == 0x97 && u[2] == 0xa5 && u[3] == 0 && u[4] == 0); - - end = append(0x3044, u); - assert (u[0] == 0xe3 && u[1] == 0x81 && u[2] == 0x84 && u[3] == 0 && u[4] == 0); - - end = append(0x10346, u); - assert (u[0] == 0xf0 && u[1] == 0x90 && u[2] == 0x8d && u[3] == 0x86 && u[4] == 0); - - //next - char* twochars = "\xe6\x97\xa5\xd1\x88"; - char* w = twochars; - int cp = next(w, twochars + 6); - assert (cp == 0x65e5); - assert (w == twochars + 3); - - char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"; - w = threechars; - cp = next(w, threechars + 9); - assert (cp == 0x10346); - assert (w == threechars + 4); - cp = next(w, threechars + 9); - assert (cp == 0x65e5); - assert (w == threechars + 7); - cp = next(w, threechars + 9); - assert (cp == 0x0448); - assert (w == threechars + 9); - - //prior - w = twochars + 3; - cp = prior (w, twochars); - assert (cp == 0x65e5); - assert (w == twochars); - - w = threechars + 9; - cp = prior(w, threechars); - assert (cp == 0x0448); - assert (w == threechars + 7); - cp = prior(w, threechars); - assert (cp == 0x65e5); - assert (w == threechars + 4); - cp = prior(w, threechars); - assert (cp == 0x10346); - assert (w == threechars); - - //previous (deprecated) - w = twochars + 3; - cp = previous (w, twochars - 1); - assert (cp == 0x65e5); - assert (w == twochars); - - w = threechars + 9; - cp = previous(w, threechars - 1); - assert (cp == 0x0448); - assert (w == threechars + 7); - cp = previous(w, threechars -1); - assert (cp == 0x65e5); - assert (w == threechars + 4); - cp = previous(w, threechars - 1); - assert (cp == 0x10346); - assert (w == threechars); - - // advance - w = twochars; - advance (w, 2, twochars + 6); - assert (w == twochars + 5); - - // distance - size_t dist = utf8::distance(twochars, twochars + 5); - assert (dist == 2); - - // utf32to8 - int utf32string[] = {0x448, 0x65E5, 0x10346, 0}; - vector utf8result; - utf32to8(utf32string, utf32string + 3, back_inserter(utf8result)); - assert (utf8result.size() == 9); - // try it with the return value; - char* utf8_end = utf32to8(utf32string, utf32string + 3, &utf8result[0]); - assert (utf8_end == &utf8result[0] + 9); - - //utf8to32 - vector utf32result; - utf8to32(twochars, twochars + 5, back_inserter(utf32result)); - assert (utf32result.size() == 2); - // try it with the return value; - int* utf32_end = utf8to32(twochars, twochars + 5, &utf32result[0]); - assert (utf32_end == &utf32result[0] + 2); - - //utf16to8 - unsigned short utf16string[] = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e}; - utf8result.clear(); - utf16to8(utf16string, utf16string + 5, back_inserter(utf8result)); - assert (utf8result.size() == 10); - // try it with the return value; - utf8_end = utf16to8 (utf16string, utf16string + 5, &utf8result[0]); - assert (utf8_end == &utf8result[0] + 10); - - //utf8to16 - char utf8_with_surrogates[] = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e"; - vector utf16result; - utf8to16(utf8_with_surrogates, utf8_with_surrogates + 9, back_inserter(utf16result)); - assert (utf16result.size() == 4); - assert (utf16result[2] == 0xd834); - assert (utf16result[3] == 0xdd1e); - // try it with the return value; - unsigned short* utf16_end = utf8to16 (utf8_with_surrogates, utf8_with_surrogates + 9, &utf16result[0]); - assert (utf16_end == &utf16result[0] + 4); - - //find_invalid - char utf_invalid[] = "\xe6\x97\xa5\xd1\x88\xfa"; - char* invalid = find_invalid(utf_invalid, utf_invalid + 6); - assert (invalid == utf_invalid + 5); - - //is_valid - bool bvalid = is_valid(utf_invalid, utf_invalid + 6); - assert (bvalid == false); - bvalid = is_valid(utf8_with_surrogates, utf8_with_surrogates + 9); - assert (bvalid == true); - - //is_bom - unsigned char byte_order_mark[] = {0xef, 0xbb, 0xbf}; - bool bbom = is_bom(byte_order_mark); - assert (bbom == true); - - ////////////////////////////////////////////////////////// - //// Unchecked variants - ////////////////////////////////////////////////////////// - - //append - memset(u, 0, 5); - end = unchecked::append(0x0448, u); - assert (u[0] == 0xd1 && u[1] == 0x88 && u[2] == 0 && u[3] == 0 && u[4] == 0); - - end = unchecked::append(0x65e5, u); - assert (u[0] == 0xe6 && u[1] == 0x97 && u[2] == 0xa5 && u[3] == 0 && u[4] == 0); - - end = unchecked::append(0x10346, u); - assert (u[0] == 0xf0 && u[1] == 0x90 && u[2] == 0x8d && u[3] == 0x86 && u[4] == 0); - - //next - w = twochars; - cp = unchecked::next(w); - assert (cp == 0x65e5); - assert (w == twochars + 3); - - w = threechars; - cp = unchecked::next(w); - assert (cp == 0x10346); - assert (w == threechars + 4); - cp = unchecked::next(w); - assert (cp == 0x65e5); - assert (w == threechars + 7); - cp = unchecked::next(w); - assert (cp == 0x0448); - assert (w == threechars + 9); - - - //previous (calls prior internally) - w = twochars + 3; - cp = unchecked::previous (w); - assert (cp == 0x65e5); - assert (w == twochars); - - w = threechars + 9; - cp = unchecked::previous(w); - assert (cp == 0x0448); - assert (w == threechars + 7); - cp = unchecked::previous(w); - assert (cp == 0x65e5); - assert (w == threechars + 4); - cp = unchecked::previous(w); - assert (cp == 0x10346); - assert (w == threechars); - - // advance - w = twochars; - unchecked::advance (w, 2); - assert (w == twochars + 5); - - // distance - dist = unchecked::distance(twochars, twochars + 5); - assert (dist == 2); - - // utf32to8 - utf8result.clear(); - unchecked::utf32to8(utf32string, utf32string + 3, back_inserter(utf8result)); - assert (utf8result.size() == 9); - // try it with the return value; - utf8_end = utf32to8(utf32string, utf32string + 3, &utf8result[0]); - assert(utf8_end == &utf8result[0] + 9); - - //utf8to32 - utf32result.clear(); - unchecked::utf8to32(twochars, twochars + 5, back_inserter(utf32result)); - assert (utf32result.size() == 2); - // try it with the return value; - utf32_end = utf8to32(twochars, twochars + 5, &utf32result[0]); - assert (utf32_end == &utf32result[0] + 2); - - //utf16to8 - utf8result.clear(); - unchecked::utf16to8(utf16string, utf16string + 5, back_inserter(utf8result)); - assert (utf8result.size() == 10); - // try it with the return value; - utf8_end = utf16to8 (utf16string, utf16string + 5, &utf8result[0]); - assert (utf8_end == &utf8result[0] + 10); - - //utf8to16 - utf16result.clear(); - unchecked::utf8to16(utf8_with_surrogates, utf8_with_surrogates + 9, back_inserter(utf16result)); - assert (utf16result.size() == 4); - assert (utf16result[2] == 0xd834); - assert (utf16result[3] == 0xdd1e); - // try it with the return value; - utf16_end = utf8to16 (utf8_with_surrogates, utf8_with_surrogates + 9, &utf16result[0]); - assert (utf16_end == &utf16result[0] + 4); -} - - diff --git a/v1_0/test_drivers/utf8reader/Makefile b/v1_0/test_drivers/utf8reader/Makefile deleted file mode 100644 index e46435c..0000000 --- a/v1_0/test_drivers/utf8reader/Makefile +++ /dev/null @@ -1,5 +0,0 @@ -CC = g++ -CFLAGS = -g -Wall -pedantic - -utf8readertest: utf8reader.cpp ../../source/utf8.h - $(CC) $(CFLAGS) utf8reader.cpp -o utf8reader diff --git a/v1_0/test_drivers/utf8reader/utf8reader.cpp b/v1_0/test_drivers/utf8reader/utf8reader.cpp deleted file mode 100644 index a1daddc..0000000 --- a/v1_0/test_drivers/utf8reader/utf8reader.cpp +++ /dev/null @@ -1,134 +0,0 @@ -#include "../../source/utf8.h" -using namespace utf8; - -#include -#include -#include -#include -using namespace std; - -int main(int argc, char** argv) -{ - if (argc != 2) { - cout << "\nUsage: utfreader filename\n"; - return 0; - } - const char* TEST_FILE_PATH = argv[1]; - // Open the test file - ifstream fs8(TEST_FILE_PATH); - if (!fs8.is_open()) { - cout << "Could not open " << TEST_FILE_PATH << endl; - return 0; - } - - // Read it line by line - unsigned int line_count = 0; - char byte; - while (!fs8.eof()) { - string line; - while ((byte = static_cast(fs8.get())) != '\n' && !fs8.eof()) - line.push_back(byte); - - line_count++; - // Play around with each line and convert it to utf16 - string::iterator line_start = line.begin(); - string::iterator line_end = line.end(); - line_end = find_invalid(line_start, line_end); - if (line_end != line.end()) - cout << "Line " << line_count << ": Invalid utf-8 at byte " << int(line.end() - line_end) << '\n'; - - // Convert it to utf-16 and write to the file - vector utf16_line; - utf8to16(line_start, line_end, back_inserter(utf16_line)); - - // Back to utf-8 and compare it to the original line. - string back_to_utf8; - utf16to8(utf16_line.begin(), utf16_line.end(), back_inserter(back_to_utf8)); - if (back_to_utf8.compare(string(line_start, line_end)) != 0) - cout << "Line " << line_count << ": Conversion to UTF-16 and back failed" << '\n'; - - // Now, convert it to utf-32, back to utf-8 and compare - vector utf32_line; - utf8to32(line_start, line_end, back_inserter(utf32_line)); - back_to_utf8.clear(); - utf32to8(utf32_line.begin(), utf32_line.end(), back_inserter(back_to_utf8)); - if (back_to_utf8.compare(string(line_start, line_end)) != 0) - cout << "Line " << line_count << ": Conversion to UTF-32 and back failed" << '\n'; - - // Now, iterate and back - unsigned char_count = 0; - string::iterator it = line_start; - while (it != line_end) { - next(it, line_end); - char_count++; - } - if (char_count != utf32_line.size()) - cout << "Line " << line_count << ": Error in iterating with next - wrong number of characters" << '\n'; - - string::iterator adv_it = line_start; - utf8::advance(adv_it, char_count, line_end); - if (adv_it != line_end) - cout << "Line " << line_count << ": Error in advance function" << '\n'; - - if (string::size_type(utf8::distance(line_start, line_end)) != char_count) - cout << "Line " << line_count << ": Error in distance function" << '\n'; - - while (it != line_start) { - previous(it, line.rend().base()); - char_count--; - } - if (char_count != 0) - cout << "Line " << line_count << ": Error in iterating with previous - wrong number of characters" << '\n'; - - //======================== Now, the unchecked versions ====================== - // Convert it to utf-16 and compare to the checked version - vector utf16_line_unchecked; - unchecked::utf8to16(line_start, line_end, back_inserter(utf16_line_unchecked)); - - if (utf16_line != utf16_line_unchecked) - cout << "Line " << line_count << ": Error in unchecked::utf8to16" << '\n'; - - // Back to utf-8 and compare it to the original line. - back_to_utf8.clear(); - unchecked::utf16to8(utf16_line_unchecked.begin(), utf16_line_unchecked.end(), back_inserter(back_to_utf8)); - if (back_to_utf8.compare(string(line_start, line_end)) != 0) - cout << "Line " << line_count << ": Unchecked conversion to UTF-16 and back failed" << '\n'; - - // Now, convert it to utf-32, back to utf-8 and compare - vector utf32_line_unchecked; - unchecked::utf8to32(line_start, line_end, back_inserter(utf32_line_unchecked)); - if (utf32_line != utf32_line_unchecked) - cout << "Line " << line_count << ": Error in unchecked::utf8to32" << '\n'; - - back_to_utf8.clear(); - unchecked::utf32to8(utf32_line.begin(), utf32_line.end(), back_inserter(back_to_utf8)); - if (back_to_utf8.compare(string(line_start, line_end)) != 0) - cout << "Line " << line_count << ": Unchecked conversion to UTF-32 and back failed" << '\n'; - - // Now, iterate and back - char_count = 0; - it = line_start; - while (it != line_end) { - unchecked::next(it); - char_count++; - } - if (char_count != utf32_line.size()) - cout << "Line " << line_count << ": Error in iterating with unchecked::next - wrong number of characters" << '\n'; - - adv_it = line_start; - utf8::unchecked::advance(adv_it, char_count); - if (adv_it != line_end) - cout << "Line " << line_count << ": Error in unchecked::advance function" << '\n'; - - if (string::size_type(utf8::unchecked::distance(line_start, line_end)) != char_count) - cout << "Line " << line_count << ": Error in unchecked::distance function" << '\n'; - - while (it != line_start) { - unchecked::previous(it); - char_count--; - } - if (char_count != 0) - cout << "Line " << line_count << ": Error in iterating with unchecked::previous - wrong number of characters" << '\n'; - - } -}